nir: Try commutative sources in CSE

Shader-db results:

GM45 NIR:
total instructions in shared programs: 4082044 -> 4081919 (-0.00%)
instructions in affected programs:     27609 -> 27484 (-0.45%)
helped:                                44

Iron Lake NIR:
total instructions in shared programs: 5678776 -> 5678646 (-0.00%)
instructions in affected programs:     27406 -> 27276 (-0.47%)
helped:                                45

Sandy Bridge NIR:
total instructions in shared programs: 7329995 -> 7329096 (-0.01%)
instructions in affected programs:     142035 -> 141136 (-0.63%)
helped:                                406
HURT:                                  19

Ivy Bridge NIR:
total instructions in shared programs: 6769314 -> 6768359 (-0.01%)
instructions in affected programs:     140820 -> 139865 (-0.68%)
helped:                                423
HURT:                                  2

Haswell NIR:
total instructions in shared programs: 6183693 -> 6183298 (-0.01%)
instructions in affected programs:     96538 -> 96143 (-0.41%)
helped:                                303
HURT:                                  4

Broadwell NIR:
total instructions in shared programs: 7501711 -> 7498170 (-0.05%)
instructions in affected programs:     266403 -> 262862 (-1.33%)
helped:                                705
HURT:                                  5
GAINED:                                4

v2: Rebase on top of Connor's fix.

v3: Convert the if-test for num_inputs == 2 to an assertion.  Suggested
by Jason after some comments / questions by Ilia.

Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com> [v1]
Reviewed-by: Jason Ekstrand <jason.ekstrand@intel.com>
Cc: Connor Abbott <cwabbott0@gmail.com>

diff --git a/src/glsl/nir/nir_opt_cse.c b/src/glsl/nir/nir_opt_cse.c
index 56d491cf9b684e49a3f8c538504a193f4e2fe339..553906e12913d830c495566777008fe291c4ad6d 100644 (file)
--- a/src/glsl/nir/nir_opt_cse.c
+++ b/src/glsl/nir/nir_opt_cse.c
@@ -37,18 +37,19 @@ struct cse_state {
 };
 
 static bool
-nir_alu_srcs_equal(nir_alu_instr *alu1, nir_alu_instr *alu2, unsigned src)
+nir_alu_srcs_equal(nir_alu_instr *alu1, nir_alu_instr *alu2, unsigned src1,
+                   unsigned src2)
 {
-   if (alu1->src[src].abs != alu2->src[src].abs ||
-       alu1->src[src].negate != alu2->src[src].negate)
+   if (alu1->src[src1].abs != alu2->src[src2].abs ||
+       alu1->src[src1].negate != alu2->src[src2].negate)
       return false;
 
-   for (unsigned i = 0; i < nir_ssa_alu_instr_src_components(alu1, src); i++) {
-      if (alu1->src[src].swizzle[i] != alu2->src[src].swizzle[i])
+   for (unsigned i = 0; i < nir_ssa_alu_instr_src_components(alu1, src1); i++) {
+      if (alu1->src[src1].swizzle[i] != alu2->src[src2].swizzle[i])
          return false;
    }
 
-   return nir_srcs_equal(alu1->src[src].src, alu2->src[src].src);
+   return nir_srcs_equal(alu1->src[src1].src, alu2->src[src2].src);
 }
 
 static bool
@@ -71,9 +72,17 @@ nir_instrs_equal(nir_instr *instr1, nir_instr *instr2)
       if (alu1->dest.dest.ssa.num_components != alu2->dest.dest.ssa.num_components)
          return false;
 
-      for (unsigned i = 0; i < nir_op_infos[alu1->op].num_inputs; i++) {
-         if (!nir_alu_srcs_equal(alu1, alu2, i))
-            return false;
+      if (nir_op_infos[alu1->op].algebraic_properties & NIR_OP_IS_COMMUTATIVE) {
+         assert(nir_op_infos[alu1->op].num_inputs == 2);
+         return (nir_alu_srcs_equal(alu1, alu2, 0, 0) &&
+                 nir_alu_srcs_equal(alu1, alu2, 1, 1)) ||
+                (nir_alu_srcs_equal(alu1, alu2, 0, 1) &&
+                 nir_alu_srcs_equal(alu1, alu2, 1, 0));
+      } else {
+         for (unsigned i = 0; i < nir_op_infos[alu1->op].num_inputs; i++) {
+            if (!nir_alu_srcs_equal(alu1, alu2, i, i))
+               return false;
+         }
       }
       return true;
    }